hive udtf 函数：输入一个字符串，将这个字符串按照特殊的逻辑处理之后，输出4个字段

这里要继承GenericUDTF 这个抽象类，直接上代码：

package com.xxx.hive.udf;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.hive.ql.exec.Description;
import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.exec.UDFArgumentLengthException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDTF;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;import java.util.ArrayList;/*** @author xxx* CREATE temporary function  details as 'com.xxx.hive.udf.Details' USING JAR '';*/
@Description(name = "details", value = "_FUNC_(expr) - ")public class Details extends GenericUDTF {@Overridepublic void close() throws HiveException {}@Overridepublic void process(Object[] objects) throws HiveException {if (objects.length == 0 || objects == null) {return;}String input = objects[0].toString();if (StringUtils.isEmpty(input)) {return;}//example dataString details = "0_0_0_0_0~0_0~0_0_0_0_25-1800~0~19~0~19_4800~0~80~0~80_21200~1~0~0~0_20600~1~0~0~0_21100~1~0~0~0;" +"1_1_1_0_9~8_9~9_0_0_27750_24-1800~0~19~0~19_4800~0~80~0~80_21200~1~0~0~0_20600~1~0~0~0_21100~1~0~0~0";String[] lines = input.split(";");for (String line : lines) {String[] arrs = line.split("-");if (arrs.length < 2) {System.out.println("+++++" + input);continue;}String[] header = arrs[0].split("_");String[] steps = arrs[1].split("_");/*BEGIN: 2024-04-02 0~0无法转数字兼容*/try {Integer.valueOf(header[3]);} catch (Exception e) {continue;}/*END: 2024-04-02 0~0无法转数字兼容*/if (header.length > 4 && Integer.valueOf(header[3]) == 2) {continue;}//过滤最后一个字段为空的情况  防止 header[9] 数组越界if (arrs[0].endsWith("_")) {continue;}if (header.length < 10) {continue;}for (int i = 0; i < steps.length; i++) {String[] step = steps[i].split("~");if (step.length < 5) {continue;}Object result = new Object[]{header[1], header[9], step[0], Integer.valueOf(step[4]) - Integer.valueOf(step[3])};forward(result);}}}/*** avoid hitting this exception:  Error in query: No handler for UDF/UDAF/UDTF*/@Overridepublic StructObjectInspector initialize(ObjectInspector[] args) throws UDFArgumentException {if (args.length != 1) {throw new UDFArgumentLengthException("xxx  takes only one argument");}if (args[0].getCategory() != ObjectInspector.Category.PRIMITIVE) {throw new UDFArgumentException("xxx  takes string as a parameter");}ArrayList<String> fieldNames = new ArrayList<String>();ArrayList<ObjectInspector> fieldOIs = new ArrayList<ObjectInspector>();fieldNames.add("moves");fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);fieldNames.add("left_moves");fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);fieldNames.add("mubiao");fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);fieldNames.add("left_num");fieldOIs.add(PrimitiveObjectInspectorFactory.javaIntObjectInspector);return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames, fieldOIs);}}